3D fluorescence microscopy data synthesis for segmentation and benchmarking.

Automated image processing approaches are indispensable for many biomedical experiments and help to cope with the increasing amount of microscopy image data in a fast and reproducible way. Especially state-of-the-art deep learning-based approaches most often require large amounts of annotated training data to produce accurate and generalist outputs, but they are often compromised by the general lack of those annotated data sets. In this work, we propose how conditional generative adversarial networks can be utilized to generate realistic image data for 3D fluorescence microscopy from annotation masks of 3D cellular structures. In combination with mask simulation approaches, we demonstrate the generation of fully-annotated 3D microscopy data sets that we make publicly available for training or benchmarking. An additional positional conditioning of the cellular structures enables the reconstruction of position-dependent intensity characteristics and allows to generate image data of different quality levels. A patch-wise working principle and a subsequent full-size reassemble strategy is used to generate image data of arbitrary size and different organisms. We present this as a proof-of-concept for the automated generation of fully-annotated training data sets requiring only a minimum of manual interaction to alleviate the need of manual annotations.

Myocardial Ischemia Induces SDF-1α Release in Cardiac Surgery Patients.

In the present observational study, we measured serum levels of the chemokine stromal cell-derived factor-1α (SDF-1α) in 100 patients undergoing cardiac surgery with cardiopulmonary bypass at seven distinct time points including preoperative values, myocardial ischemia, reperfusion, and the postoperative course. Myocardial ischemia triggered a marked increase of SDF-1α serum levels whereas cardiac reperfusion had no significant influence. Perioperative SDF-1α serum levels were influenced by patients' characteristics (e.g., age, gender, aspirin intake). In an explorative analysis, we observed an inverse association between SDF-1α serum levels and the incidence of organ dysfunction. In conclusion, time of myocardial ischemia was identified as the key stimulus for a significant upregulation of SDF-1α, indicating its role as a marker of myocardial injury. The inverse association between SDF-1α levels and organ dysfunction association encourages further studies to evaluate its organoprotective properties in cardiac surgery patients.